© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 89909
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_18_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     выйти
    0.54
     motel
    0.51
     деклара
    0.49
    ኹ
    0.48
     freestyle
    0.47
     alimentación
    0.47
     journalism
    0.46
     degeneracy
    0.46
     anarchist
    0.46
     motivated
    0.45
    POSITIVE LOGITS
    ل
    0.63
    اتف
    0.53
    عود
    0.52
    ات
    0.45
    yin
    0.44
     Limitation
    0.44
    αρ
    0.44
     $=\
    0.43
     اتھار
    0.43
    زند
    0.42
    Activations Density 0.000%

    No Known Activations